• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.3
• /
• pp.259-266
• /
• 2011

We present a new dual sequential approximate optimization (SAO) algorithm called SD-TDQAO (sequential dual two-point diagonal quadratic approximate optimization). This algorithm solves engineering optimization problems with a nonlinear objective and nonlinear inequality constraints. The two-point diagonal quadratic approximation (TDQA) was originally non-convex and inseparable quadratic approximation in the primal design variable space. To use the dual method, SD-TDQAO uses diagonal quadratic explicit separable approximation; this can easily ensure convexity and separability. An important feature is that the second-derivative terms of the quadratic approximation are approximated by TDQA, which uses only information on the function and the derivative values at two consecutive iteration points. The algorithm will be illustrated using mathematical and topological test problems, and its performance will be compared with that of the MMA algorithm.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.7
• /
• pp.139-148
• /
• 2012

An ensemble of classifiers is to employ a set of individually trained classifiers and combine their predictions. It has been found that in most cases the ensembles produce more accurate predictions than the base classifiers. Combining outputs from multiple classifiers, known as ensemble learning, is one of the standard and most important techniques for improving classification accuracy in machine learning. An ensemble of classifiers is efficient only if the individual classifiers make decisions as diverse as possible. Bagging is the most popular method of ensemble learning to generate a diverse set of classifiers. Diversity in bagging is obtained by using different training sets. The different training data subsets are randomly drawn with replacement from the entire training dataset. The random subspace method is an ensemble construction technique using different attribute subsets. In the random subspace, the training dataset is also modified as in bagging. However, this modification is performed in the feature space. Bagging and random subspace are quite well known and popular ensemble algorithms. However, few studies have dealt with the integration of bagging and random subspace using SVM Classifiers, though there is a great potential for useful applications in this area. The focus of this paper is to propose methods for improving SVM performance using hybrid ensemble strategy for bankruptcy prediction. This paper applies the proposed ensemble model to the bankruptcy prediction problem using a real data set from Korean companies.

• Asian Journal of Atmospheric Environment
• /
• v.11 no.2
• /
• pp.122-130
• /
• 2017

The main purpose of the study was to clarify the properties of individual particles collected at each behavior space of a factory worker. The samplings of size-segregated ($PM_{2.1-1.1}$ and $PM_{4.7-3.3}$) indoor particles were conducted at three different behavior spaces of a factory worker who is engaged in an auto parts manufacturing plant (i.e., his home, his work place in factory, and his favorite restaurant). Elemental specification (i.e., relative elemental content and distribution in and/or on individual particles) was performed by a micro-PIXE system. Every element detected from the coarse particulate matters of home was classified into three groups, i.e., a group of high net-counts (Na, Al, and Si), a group of intermediate net-counts (Mg, S, Cl, K, and Ca), and a group of minor trace elements (P, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, and Pb). The results of EF for $PM_{4.7-3.3}$ in home indicated that several heavy metals were generated from the sources within the house itself. An exceptional feature shown in the individual particles in workplace is that Cr, Mn, and Co were clearly detected in both fine and coarse particles. Cluster analysis suggested that the individual coarse particles ($PM_{4.7-3.3}$) collected at the indoor of factory were chemically heterogeneous and they modified with sea-salt, mineral, and artificially derived elements. The principal components in individual coarse particles collected at restaurant were sea-salt and mineral without mixing with harmful trace elements like chromium and manganese. Compared to the indoor fine particles of home and restaurant, many elements, especially, Cl, Na, Cr, Mn, Pb, and Zn showed overwhelmingly high net-counts in those of factory.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.60 no.2
• /
• pp.65-73
• /
• 2018

This study aims to analyzes the Relationship Between Community Consciousness and Residents' Participation in Tourism Development. Starting in 2004, the Rural Tourism Development Project, which has been promoted in Korea, is taking a bottom-up approach that values the participation of residents. And Resident's Participation is also an important criterion for selecting business sites. As the farming community becomes more modern, the community consciousness is declining. But Community consciousness is an important factor for the sustainable maintenance of rural villages. And if community members share a sense of homogeneity, they can identify problems that communities have, and they can solve them with responsibility. Community consciousness can be called the basic infrastructure of residents' participation. Rural tourism feature different characteristics from other tourist areas in that the residential space of local residents is the destination of the tours. As a result, the influence on tourism development is directly affected, so the attitude of local residents is an important success factor unlike other tourism developments. The study analyzed the community consciousness and participation in Tourism Development, which is a significant success factor in rural areas. The survey which included 200 residents of the DMZ Peace Village Site, was concluded that the member's perception and ttachment among Community Consciousness affected the Residents' Participation, and that Economic Influence among tourist development attitudes affected the Residents' Participation. It based on the results in rural tourism development for the residents' participation should be considered with a plan to enhance the economic life satisfaction and promote the economic impact on the area.

• Archives of design research
• /
• v.14 no.4
• /
• pp.25-33
• /
• 2001

With the increasing access to the internet, the number of designers who rely on internet to use information on design is on the rise. Therefore common dictionary of design terminology need to be formed and shared among designers. To do so, internet is very useful medium. However as relating terminology increases rapidly through interactivity among designers, it will be far from taking full advantage of features of internet to set up and provide such information unilaterally on internet. This indicates that providing data on the internet, not via traditional books, requires in-depth study on process of establishment of database structure and appropriate interface design. Thus this study will show design terms database model that harnesses internet feature that enables establishment of information spontaneously through user's interactivity, departing from a model that conveys information unilaterally. This report summarized and analyzed various models and suggested classification system in accordance with user's learning cognition. Problems on existing dictionary of design terminology were identified and new methods addressing such problems were exploited. In a word, this report is intended to propose user oriented inter-constructive database model that highlights high level of openness and interactivity by enabling changes of text in the cyber space and encouraging user to participate in making design dictionary.

• Archives of design research
• /
• v.19 no.5 s.67
• /
• pp.151-160
• /
• 2006

When it comes to the paintings in Joseon Dynasty, landscape and a genre paintings were popular but it was Minhwa that people of every dass loved. Minhwa contained not only true meaning of a picture, but also it was simple and straighforwardly depicted. Among them, paintings in books belonging to the Joseon Dynasty (hereinafter called Checkgeori paintings) describe a small universe in which people live harmoniously in nature on the basis of a Confucian society. In addition, it shows modern philosophy in paintings and makes a feature of human life. In this paper, 'Ssangpok Checkgeori 'in Checkgeori paintings illustrates the relationships between things such as color, arrangement, place and direction. They have outstanding features such as the direction of things in composition, multiple vanishing points, a folding screen constituent and movement of viewpoints. Therefore, we come to know the painting method of 'Ssangpok Checkgeori' can be applied to modern paintings.

• Environmental and Resource Economics Review
• /
• v.16 no.4
• /
• pp.803-832
• /
• 2007

Electricity and heat load profiles by use types on an hourly basis at the least are essential for assessing economic viability of new cogeneration and CES projects and for optimally operating existing cogeneration and CES facilities. We adopt a multilevel model to specify heat load profiles so as to utilize in a flexible manner the panel nature of our data on weather and heating/cooling use. Converting the multilevel model to the linear mixed-effects model, we estimate the model by panel FGLS. The estimated load profile model for each distinct use type accounts for the effects of temperature, humidity, each hour over the year, each day of the week, each type of legal holidays, and heating/cooling area on energy use. To save space, we feature in detail the heating profile of the household.

• Journal of Korea Multimedia Society
• /
• v.15 no.6
• /
• pp.761-769
• /
• 2012

In this paper, a setting method of initial cluster centers and color image segmentation using superpixels and Fuzzy C-means(FCM) algorithm is proposed. Generally, the FCM can be widely used to segment color images, and an element is assigned to any cluster with each membership values in the FCM. However the algorithm has a problem of local convergence by determining the initial cluster centers. So the selection of initial cluster centers is very important, we proposed an effective method to determine the initial cluster centers using superpixels. The superpixels can be obtained by grouping of some pixels having similar characteristics from original image, and it is projected $La^*b^*$ feature space to obtain the initial cluster centers. The proposed method can be speeded up because number of superpixels are extremely smaller than pixels of original image. To evaluate the proposed method, several color images are used for computer simulation, and we know that the proposed method is superior to the conventional algorithm by the experimental results.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2002.07b
• /
• pp.976-979
• /
• 2002

A focusing grating coupler (FGC) was not fabricated by the 'Continuous Path Control' writing strategy but by an electron-beam lithography system of more general exposure mode, which matches not only the address grid with the grating period but also an integer multiple of the address grid resolution (5 nm), To more simplify the fabrication, we are able to reduce a process step without large decrease of pattern quality by excluding a conducting material or layer such as metal (Al, Cr, Au), which are deposited on top or bottom of an e-beam resist to prevent charge build-up during e-beam exposure. A grating pitch period and an aperture feature size of the FGC designed and fabricated by e-beam lithography and reactive ion etching were ranged over 384.3 nm to 448.2 nm, and $0.5{\times}0.5mm^2$ area, respectively, This fabrication method presented will reduce processing time and improve the grating quality by means of a consideration of the address grid resolpution, grating direction, pitch size and shapes when exposing. Here our investigations concentrate on the design and efficient fabrication results of the FGC for coupling from slab waveguide to a spot in free space.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.457-461
• /
• 2010

Even though face recognition researches have been developed for a long ago, there is no practical face recognition system in real life. It is caused by several real situations where non-facial components such as glasses, scarf, and hair occlude facial components while facial images in a face database are well designed. This occlusion decreases recognition performance. Previous approaches in recent years have tried to solve non-facial components but have not resulted in enough performance. In this paper, we propose a method to handle this problem based on support vector data description, which trains the hyperball in feature space to find the minimum distance estimating the approximated face. In order to evaluate its performance and validate the effectiveness of the proposed method, we make several experiments and the results show that the proposed method has a considerable effectiveness.